MERA - ruHumanEval: leaderboard
MERA is the Russian open benchmark run by the AI Alliance Russia; this is its ruHumanEval task: the Russian HumanEval port, scored by unit tests. Each MERA task keeps its own native metric, so the boards are not on one shared scale.
Metric: pass@1 (%). Source: mera.a-ai.ru. Saturation forecast: Not forecast. 631 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.6 27B | 79.51 | #170 |
| 2 | Qwen 3 4B 2507 (Thinking) | 77.44 | #538 (Qwen 3 4B 2507) |
| 3 | Qwen 3.6 35B A3B | 76.59 | #226 |
| 4 | Qwen 3 4B | 76.16 | #829 |
| 5 | Qwen 3 235B A22B 2507 (Thinking) | 75.98 | #260 (Qwen 3 235B A22B 2507) |
| 6 | Gemini 2.0 Flash | 73.66 | #342 |
| 7 | GPT-4o Mini | 70.37 | #599 |
| 8 | Qwen 3 14B | 64.09 | #537 |
| 9 | GigaChat 2 Pro | 62.74 | #682 |
| 10 | Qwen 3 32B | 62.56 | #443 |
| 11 | Qwen 3 30B A3B 2507 (Thinking) | 62.32 | #376 (Qwen 3 30B A3B 2507) |
| 12 | Qwen 3 Next 80B A3B (Thinking) | 61.71 | #320 (Qwen 3 Next 80B A3B) |
| 13 | Gemma 4 31B (IT) | 61.65 | #176 |
| 14 | Gemini 1.5 Flash | 61.04 | #618 |
| 15 | Qwen 3 8B | 60.91 | #674 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=mera-ruhumaneval · How It Works · Data refreshed daily, snapshot 2026-10-20.